MCP-Server

scrapewright

io.github.Ozymandias-Owens-2/scrapewright
Daten & Analytik Öffentlich und erreichbar MCP 2025-11-25

Was dieses MCP kann

Detects website platforms and extracts structured data from individual pages or crawled sites using reusable parsing recipes.

account
Credits left and this month's usage for the key in use.
Eingabeschema
{'type': 'object', 'title': 'accountArguments', 'properties': {}}
Ausgabeschema
{'type': 'object', 'title': 'accountDictOutput', 'additionalProperties': True}
crawl_site
Walk a site and extract every item. Waits up to four minutes; a longer crawl returns a job_id to pass to crawl_status. `mode` picks how the items are found. "rows" (the default) reads every card on the listing itself and follows its pagination -- right for search results, categories and tables. "links" follows each card into its own page, for sites where an item has one. "like" starts from one example item page, given as `like_page`, and finds every other page shaped like it; pass `listing_url` as well when you know the stock or results page, because inferring it is the part that fails.
Eingabeschema
{'type': 'object', 'title': 'crawl_siteArguments', 'required': ['listing_url'], 'properties': {'js': {'type': 'boolean', 'title': 'Js', 'default': False}, 'mode': {'type': 'string', 'title': 'Mode', 'default': 'rows'}, 'fields': {'anyOf': [{'type': 'array', 'items': {'type': 'string'}}, {'type': 'null'}], 'title': 'Fields', 'default': None}, 'scroll': {'type': 'integer', 'title': 'Scroll', 'default': 0}, 'like_page': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Like Page', 'default': None}, 'max_items': {'type': 'integer', 'title': 'Max Items', 'default': 25}, 'listing_url': {'type': 'string', 'title': 'Listing Url'}}}
Ausgabeschema
{'type': 'object', 'title': 'crawl_siteDictOutput', 'additionalProperties': True}
crawl_status
Fetch a crawl that outlived its call.
Eingabeschema
{'type': 'object', 'title': 'crawl_statusArguments', 'required': ['job_id'], 'properties': {'job_id': {'type': 'string', 'title': 'Job Id'}}}
Ausgabeschema
{'type': 'object', 'title': 'crawl_statusDictOutput', 'additionalProperties': True}
detect_site
Report what platform a site runs on and which strategy to use. Cheap; call it before a large job.
Eingabeschema
{'type': 'object', 'title': 'detect_siteArguments', 'required': ['url'], 'properties': {'url': {'type': 'string', 'title': 'Url'}}}
Ausgabeschema
{'type': 'object', 'title': 'detect_siteDictOutput', 'additionalProperties': True}
extract_page
Extract structured data from ONE page. ``fields`` declares your own schema, e.g. ["title", "salary:number", "tags:list"]; omit it for the product schema. First call on a new site compiles a recipe (300 credits); later calls replay it for 1 credit per row. A site nobody could read is remembered for a week and answered without calling the model, so re-reading a dead page costs nothing. `retry` asks anyway.
Eingabeschema
{'type': 'object', 'title': 'extract_pageArguments', 'required': ['url'], 'properties': {'js': {'type': 'boolean', 'title': 'Js', 'default': False}, 'url': {'type': 'string', 'title': 'Url'}, 'retry': {'type': 'boolean', 'title': 'Retry', 'default': False}, 'fields': {'anyOf': [{'type': 'array', 'items': {'type': 'string'}}, {'type': 'null'}], 'title': 'Fields', 'default': None}}}
Ausgabeschema
{'type': 'object', 'title': 'extract_pageDictOutput', 'additionalProperties': True}
Geändert
crawl_site
3. October 2026 02:50
Geändert
extract_page
3. October 2026 02:50
Hinzugefügt
account
21. September 2026 02:40
Hinzugefügt
crawl_status
21. September 2026 02:40
Hinzugefügt
crawl_site
21. September 2026 02:40
Hinzugefügt
extract_page
21. September 2026 02:40
Hinzugefügt
detect_site
21. September 2026 02:40